On the relevance of language in speaker recognition

TL;DR

This study investigates how language differences affect speaker recognition accuracy by analyzing a bilingual database with Spanish and Catalan speakers using vector quantization and covariance matrix methods.

Contribution

It introduces a bilingual speaker database and evaluates the impact of language on recognition performance with two distinct methods.

Findings

Language differences significantly influence speaker recognition results.

Vector quantization and covariance matrix methods show varying sensitivity to language effects.

The research highlights the importance of considering language in speaker recognition systems.

Abstract

This paper presents a new database collected from a bilingual speakers set (49), in two different languages: Spanish and Catalan. Phonetically there are significative differences between both languages. These differences have let us to establish several conclusions on the relevance of language in speaker recognition, using two methods: vector quantization and covariance matrices